检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Gao, Rujun Guo, Xiaosu Li, Xiaodi Narayanan, Arun Balajiee Lekshmi Thomas, Naveen Srinivasa, Arun R. Department of Mechanical Engineering Texas A&M University J. Mike Walker '66 United States Computer Science Department University of Texas at Dallas United States Intelligent Systems Program University of Pittsburgh United States Department of Artificial Intelligence and Informatics Mayo Clinic United States

This study explores the feasibility of using large language models (LLMs), specifically GPT-4o (ChatGPT), for automated grading of conceptual questions in an undergraduate Mechanical engineering course. We compared the grading performance of GPT-4o with that of human teaching assistants (TAs) on ten quiz problems from the MEEN 361 course at Texas A&M University, each answered by approximately 225 students. Both the LLM and TAs followed the same instructor-provided rubric to ensure grading consistency. We evaluated performance using Spearman's rank correlation coefficient and Root Mean Square Error (RMSE) to assess the alignment between rankings and the accuracy of scores assigned by GPT-4o and TAs under zero- and few-shot grading settings. In the zero-shot setting, GPT-4o demonstrated a strong correlation with TA grading, with Spearman's rank correlation coefficient exceeding 0.6 in seven out of ten datasets and reaching a high of 0.9387. Our analysis reveals that GPT-4o performs well when grading criteria are straightforward but struggles with nuanced answers, particularly those involving synonyms not present in the rubric. The model also tends to grade more stringently in ambiguous cases compared to human TAs. Overall, ChatGPT shows promise as a tool for grading conceptual questions, offering scalability and consistency. © 2024, CC BY-NC-ND.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Improvement of Spatial Ambiguity in Multi-Channel Speech Separation Using Channel Attention

Improvement of Spatial Ambiguity in Multi-Channel Speech Sep...

引用

2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021

作者： Hong, Qian-Bei Wu, Chung-Hsien Nguyen, Thanh Binh Wang, Hsin-Min National Cheng Kung University and Academia Sinica Graduate Program of Multimedia Systems and Intelligent Computing Tainan Taiwan National Cheng Kung University Department of Computer Science and Information Engineering Tainan Taiwan

ISBN: (纸本)9789881476890

Multi-channel speech separation has been successfully applied in a complex real-world environment such as the far-field condition. The common solution to deal with the far-field condition is using a multi-channel signal captured by a structured microphone array and leveraging the inner difference between channels to enhance the speech separation performance. The spatial feature has been widely used in recent speech separation research. This feature appears to be insufficient when the location information becomes ambiguous. This is known as the spatial ambiguity problem. In order to deal with the spatial ambiguity problem, this study proposes an attention mechanism for the Temporal-Spatial Neural Filter (TSNF), in which the channel attention on merged features and the feature map of 1D convolution block in the temporal convolution network is proposed. The proposed method is evaluated on the multi-channel reverberant dataset which is built based on the WSJ0-2mix dataset. The dataset is simulated in the real-environment room by using the Room Impulse Response generator. In the experimental results, the proposed methods produced the SI -SNR improvement of about 1.2dB in close speakers' case, while a small decrease of 0.1dB in other cases. © 2021 APSIPA.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Behavioral Aspects of Implementing Green IT in an Academic Environment

Analyzing the Behavioral Aspects of Implementing Green IT in...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Dedy Syamsuar Fero Triando Maria Ulfa Darius Antoni Adele Mailangkay Deden Witarsyah Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia Postgradute Department Universitas Bina Darma Palembang Indonesia Information System Study Program Computer Science Faculty Universitas Bina Darma Palembang Indonesia Faculty of Computer Science Universitas Indo Global Mandiri Palembang Indonesia School of Industrial Engineering Telkom University Bandung Indonesia

Environmental awareness has recently emerged as one of the most crucial topics. As a result, various groups advocate for these technologies and research ways to promote their usage in various contexts. This study examines the factors influencing the intention and use of green technology among academics. This study integrates Price Value (PV) and Consideration of future consequence (CFC) to Theory Planned Behavior (TPB) as a theoretical basis. Two hundred five valid replies were gathered and processed through statistical analysis. The results of this study partly support the developed hypotheses. Four hypotheses developed from TPB have presented significant relationships. However, PV and CFC were not. The findings indicate that individuals in this study did not consider CFC or PV of green IT products as critical factors in their decision-making process. Findings also suggest that for implementation success, competent parties must consider the campaign to increase individual awareness and provide financial support regarding environmental policy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic programming Algorithm using Furniture Industry 0/1 Knapsack Problem

Dynamic Programming Algorithm using Furniture Industry 0/1 K...

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Mietha Anditta Natashya Amartya Laurens Spits Warnars Harco Leslie Hendric Spits Warnars Arief Ramadhan Teddy Siswanto Teddy Mantoro Nurulhuda Noordin Computer Science Departement School of Computer Science Bina Nusantara University Jakarta Indonesia Information Systems Departement School of Information Systems Bina Nusantara University Jakarta Indonesia Computer Science Departement BINUS Graduate Program - Computer Science Bina Nusantara University Jakarta Indonesia PJJ Informatika Telkom University Bandung Indonesia Information Systems Department Trisakti University Jakarta Indonesia Faculty of Engineering and Technology Sampoerna University Jakarta Indonesia School of Computing Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Selangor Malaysia

Dynamic programming is a fundamental algorithm that can be found in our daily lives easily. One of the dynamic programming algorithm implementations consists of solving the 0/1 knapsack problem. A 0/1 knapsack problem can be seen from industrial production cost. It is prevalent that a production cost has to be as efficient as possible, but the expectation is to get the proceeds of the products higher. Thus, the dynamic programming algorithm can be implemented to solve the diverse knapsack problem, one of which is the 0/1 knapsack problem, which would be the main focus of this paper. The implementation was implemented using C language. This paper was created as an early implementation algorithm using a Dynamic program algorithm applied to an Automatic Identification System (AIS) dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detecting defects of railway tracks by using computer vision methodology

Detecting defects of railway tracks by using computer vision...

引用

IISE Annual Conference and Expo 2021

作者： Ravishankar, Premkumar Tokgoz, Berna Eren Zhang, Xulong Zhang, Jing Hwang, Seokyon Department of Industrial and Systems Engineering Lamar University BeaumontTX United States Department of Computer Science Lamar University BeaumontTX United States Construction Management Program Lamar University BeaumontTX United States

ISBN: (纸本)9781713838470

Maintaining railway tracks in healthy conditions is critical to ensuring the safe operation of railroad transportation. According to the Federal Railroad Administration (FRA), nearly 23% of train accidents that occurred between 2015 to 2020 were due to the defects of the tracks. In an effort to prevent such accidents, railway companies regularly inspect tracks to detect and fix defects of track systems. This research proposes an innovative method for conducting railroad track inspection to enhance the maintenance operation. The proposed approach aims to overcome the existing inspection practices based on human observation that is costly, time-consuming, and error prone. To this end, the proposed method utilizes computer vision methodologies to achieve high-level automation and accuracy of defect detection through the analysis of digital images. The outcome of this study is envisioned to help railway companies perform predictive maintenance more effectively and, thereby, reduce the risk of train accidents and increase the resiliency of their assets. © 2021 IISE Annual Conference and Expo 2021. All rights reserved.

关键词： Railroad tracks

来源：评论

学校读者我要写书评

暂无评论

Biomimetic Frontend for Differentiable Audio Processing

arXiv

引用

arXiv 2024年

作者： Famularo, Ruolan Leslie Zotkin, Dmitry N. Shamma, Shihab A. Duraiswami, Ramani Perceptual Interfaces and Reality Lab. Computer Science & UMIACS University of Maryland College Park United States Department of Linguistics University of Maryland College Park United States Program in Neuroscience & Cognitive Science University of Maryland College Park United States Institute of Systems Research & Electrical and Computer Engineering University of Maryland College Park United States

While models in audio and speech processing are becoming deeper and more end-to-end, they as a consequence need expensive training on large data, and are often brittle. We build on a classical model of human hearing and make it differentiable, so that we can combine traditional explainable biomimetic signal processing approaches with deep-learning frameworks. This allows us to arrive at an expressive and explainable model that is easily trained on modest amounts of data. We apply this model to audio processing tasks, including classification and enhancement. Results show that our differentiable model surpasses black-box approaches in terms of computational efficiency and robustness, even with little training data. We also discuss other potential applications. © 2024, CC BY-NC-ND.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

IoT for Water Quality Categorization

IoT for Water Quality Categorization

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Hermantoro Sastrohartono Andreas Wahyu Krisdiarto Arief Ika Uktoro Reza Rahutomo Teddy Suparyanto Bens Pardamean Agricultural Engineering Department Faculty of Agricultural Technology Institute of Agriculture STIPER Yogyakarta Indonesia Information System Department School of Information Systems Bina Nusantara University Jakarta Indonesia Bioinformatics & Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia

In agricultural water research, the adoption of Internet of Things (IoT) technology has emerged as a pivotal approach for large-scale data collection. Water availability in the context of water quality is very important, both for domestic and industrial purposes. For domestic purposes, drinking water and bathing water are separated. Meanwhile, for the palm oil industry, boiler filler is differentiated from additional process water (dilution water). Water quality parameters can be assessed from turbidity and Total Dissolve Solid (TDS). Measurements using measuring instruments separately and repeatedly require significant energy, time, and costs. This research was conducted with the primary objective of presenting a novel method for categorizing water quality with the approach of IoT sensor technology. The research methodology entailed the utilization of an integrated IoT water sensors system in conjunction with manual water categorization. The methods consist of (1) system design, (2) design and installation of sensor and IoT-based microcontrollers, and (3) accuracy and precision testing compared with laboratory measurements. The precision of the integrated IoT water sensors was assessed through a dedicated sensor precision test, resulting in an accuracy rate of 94.4% for the turbidity sensor and 97.5% for the TDS sensor. Notably, this approach successfully discriminated drinking water with valid categorization, while other water types, including groundwater, water with tea, and water with coffee, yielded null categorization results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Supply Chain Sustainability in Disruption: SC Intelligence, Customer Knowledge Transfer, and the Mediating Role of IS/IT

引用

IEEE engineering Management Review 2025年

作者： Ratna, Silvia Saide, Saide Rater, Salya Svyazhanovna, Baizakova Saule Herzavina, Herzavina Faculty of Information Technology Department of Informatics Engineering and Department of Information Systems Banjarmasin Indonesia State Islamic University of Sultan Syarif Kasim Riau Universitas Islam Negeri Sultan Syarif Kasim Riau-UIN SUSKA Riau Department of Information Systems Faculty of Science and Technology Indonesia PRO Knowledge Indonesia Pekanbaru Indonesia Universitas Pahlawan Tuanku Tambusai Indonesia Lembaga Enreach UIN Suska Riau Indonesia Politeknik Aceh Selatan Department of Informatics Engineering Aceh Indonesia Information Communication Technologies Robotics in Arkalyk Pedagogical Institute Master of Natural Sciences Educational Program for the Informatics Computer Science Kazakhstan Universitas Pahlawan Tuanku Tambusai Department of Informatics Engineering Indonesia National Taiwan University of Science and Technology Taiwan

Knowledge resource and information system/technology (IS/IT) capability have been considered to improve firm performance, however there is still a gap regarding the sustainability of supply chain to face and recover from disruption (e.g., COVID-19). Questionnaire-based surveys was adopted and received feedback from sixty (160) Indonesian companies or about 28.07% of response rate. © 1973-2011 IEEE.

关键词： customer knowledge transfer disruption information system/technology (IS/IT) responding knowledge management resource-based view (RBV) Supply chain (SC) sustainability supply chain knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

Rice Variety Identification Using Edge Feature Extraction and Texture-Based Segmentation

Rice Variety Identification Using Edge Feature Extraction an...

引用

International Seminar on Application for Technology of Information and Communication (ISemantic)

作者： Aji Setiawan Kusworo Adi Catur Edi Widodo Doctoral Program of Information Systems School of Postgraduate Studies Diponegoro University Semarang Indonesia Department of Information Technology Faculty of Engineering Darma Persada University Jakarta Indonesia School of Postgraduate Studies Diponegoro University Semarang Indonesia Department of Physics Faculty of Science and Mathematics Diponegoro University Semarang Indonesia

This research proposes a methodology for identifying the optimal feature combination using Support Vector Machine (SVM) based on edge and texture features. Canny, Sobel, and Prewitt for edge detection and GLCM, Gabor, and LBP for texture analysis are popular feature extraction techniques widely employed in various cases. The approach combines edge and texture features with SVM to classify rice types into five categories: Ipsala, Jasmine, Karacadag, Arborio, and Basmati. Experimental results demonstrate that SVM using Canny, Sobel, and Prewitt combined Gabor texture features outperforms the comparative methods. A comparative analysis based on accuracy scores using confusion matrices is conducted. Combining all feature edge methods, Canny, Sobel, and Prewitt with Gabor on SVM classification is the best model for rice object classification, achieving an accuracy of 96%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Smart Analysis of Performing Scalable Inference for Big Data Analytics

The Smart Analysis of Performing Scalable Inference for Big ...

引用

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Vishakha D Bhandarkar Aruna Sri Rongali Mohamed Dawood Shamout Prof. Sachin Pund Gigih Forda Nama Shrishailappa Patil Applied Mathematics and Humanities Yeshwantrao Chavan College of Engineering India Graduate Doctoral Information Technology/Graduate (Information Technology Emphasis/Information Technology Ph.D.) University of The Cumberlands US Department of Management College of Business Administration University of Sharjah Sharjah United Arab Emirates Department of Industrial Engineering Shri Ramdeobaba College of Engineering and Management Nagpur Maharashtra India Department of Informatics Doctoral Program of Environtmental Science University of Lampung Bandar Lampung Computer engineering Vishwakarma Institute of Technology Pune

This paper examines the reproducibility of massive information analytics under particular factors. The paper proposes the “performing Scalable Inference” technique to cope with scalability troubles and to exploit current big statistics platforms for efficient computing and statistics garage of the statistics. In particular, the paper describes how to perform leak-free, parallelizable visible analytics over massive datasets using present extensive records analytics frameworks such as Apache Flink. This method presents an automated manner to execute analytics that preserves reproducibility and the ability to make adjustments without re-running the entire technique. The paper also demonstrates how these analytics may help several real-world use instances, explore affected person cohorts for studies, and develop stratified patient cohorts for hospital therapy. In the end, the paper observes how the proposed method may be exercised within the real world. Actively scalable inference for massive information analytics is pivotal in optimizing decision-making and allocation of assets. Typically, such inferences are made based on information accumulated from numerous sources, databases, unstructured data, and different digital sources. So one can ensure scalability, a complete cloud-primarily based platform has to be hired. This solution will permit the ***, deploying the essential records series and evaluation algorithms are prime here. It could permit the platform to recognize the styles inside the statistics and discover any ability correlations or traits. Additionally, predictive analytics and system mastering strategies may be incorporated to provide insights into the results of the information. In the long run, by leveraging those techniques, the platform can draw efficient inferences and appropriately compare situations in an agile and green way..

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：